WZMIAOMIAO/deep-learning-for-image-processing · error · ValueError

expected stages_out_channels as list of 5 positive ints

Error message

expected stages_out_channels as list of 5 positive ints

What it means

ShuffleNetV2.__init__ requires stages_out_channels to contain exactly 5 entries (conv1 output plus the three stages plus the final conv5) and raises ValueError otherwise. Each entry fixes the output channel count of a corresponding layer group.

Source

Thrown at pytorch_classification/Test7_shufflenet/model.py:95

            out = torch.cat((self.branch1(x), self.branch2(x)), dim=1)

        out = channel_shuffle(out, 2)

        return out


class ShuffleNetV2(nn.Module):
    def __init__(self,
                 stages_repeats: List[int],
                 stages_out_channels: List[int],
                 num_classes: int = 1000,
                 inverted_residual: Callable[..., nn.Module] = InvertedResidual):
        super(ShuffleNetV2, self).__init__()

        if len(stages_repeats) != 3:
            raise ValueError("expected stages_repeats as list of 3 positive ints")
        if len(stages_out_channels) != 5:
            raise ValueError("expected stages_out_channels as list of 5 positive ints")
        self._stage_out_channels = stages_out_channels

        # input RGB image
        input_channels = 3
        output_channels = self._stage_out_channels[0]

        self.conv1 = nn.Sequential(
            nn.Conv2d(input_channels, output_channels, kernel_size=3, stride=2, padding=1, bias=False),
            nn.BatchNorm2d(output_channels),
            nn.ReLU(inplace=True)
        )
        input_channels = output_channels

        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)

        # Static annotations for mypy
        self.stage2: nn.Sequential
        self.stage3: nn.Sequential

View on GitHub (pinned to 1ec3fe6f37)

Solutions

1. Provide 5 channel counts, e.g. [24, 116, 232, 464, 1024] for the 1.0x model.
2. Use the provided presets ShuffleNetV2_x0_5/x1_0/x1_5/x2_0(num_classes=...) which hard-code valid lists.
3. Verify the order of positional args: stages_repeats first (3 items), stages_out_channels second (5 items).

Example fix

// before
model = ShuffleNetV2(stages_repeats=[4, 8, 4], stages_out_channels=[116, 232, 464, 1024], num_classes=5)
// after
model = ShuffleNetV2(stages_repeats=[4, 8, 4], stages_out_channels=[24, 116, 232, 464, 1024], num_classes=5)

assert len(stages_out_channels) == 5, f"stages_out_channels must have 5 ints, got {len(stages_out_channels)}"
model = ShuffleNetV2(stages_repeats=stages_repeats, stages_out_channels=stages_out_channels, num_classes=n)

def valid_channels(c) -> bool:
    return isinstance(c, list) and len(c) == 5 and all(isinstance(v, int) and v > 0 for v in c)

try:
    model = ShuffleNetV2(stages_repeats=rep, stages_out_channels=ch, num_classes=n)
except ValueError as e:
    if "stages_out_channels" in str(e):
        model = ShuffleNetV2_x1_0(num_classes=n)
    else:
        raise

When it happens

Trigger: Calling ShuffleNetV2 with stages_out_channels of length != 5 — e.g. [24, 116, 232, 464] (missing the last conv5 value) or [116, 232, 464, 1024] (only the stages).

Common situations: Defining a custom width variant and omitting the leading 24 (first conv) or trailing 1024 (last conv) value; truncating a copied preset list; confusing the channel list with the repeats list.

Related errors

• expected stages_repeats as list of 3 positive ints
• illegal stride value.
• The inverted_residual_setting should not be empty.
• illegal stride value.
• image: {} isn't RGB mode.

AI-assisted analysis of WZMIAOMIAO/deep-learning-for-image-processing@1ec3fe6f37 (2026-08-30). Data as JSON: /api/errors/ff0c7ec902fe60da. Report an issue: GitHub.